Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and indicators within a structured argument or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific contexts or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndInit
    -0.47
     الحره
    -0.38
     fortfarande
    -0.36
     Offisielt
    -0.36
    JsonIgnore
    -0.35
     Pakai
    -0.34
     Perlu
    -0.33
    DebuggerNonUser
    -0.32
     distinguished
    -0.32
    httphttps
    -0.31
    POSITIVE LOGITS
    RegressionTest
    0.61
    #+#
    0.58
    StructEnd
    0.57
    enumii
    0.56
    ArrowToggle
    0.56
     насељу
    0.55
     betweenstory
    0.54
     ModelRenderer
    0.54
    yntaxException
    0.53
    enumi
    0.52
    Act Density 0.429%

    No Known Activations