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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that express similarity

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

    comparisons using "like"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.52
    MLLoader
    -0.47
    styleType
    -0.47
    hésite
    -0.44
    ContentAlignment
    -0.43
    FlatStyle
    -0.43
     Bewer
    -0.42
     عج
    -0.42
     freaked
    -0.41
    CompilerServices
    -0.41
    POSITIVE LOGITS
     Wikimedijinoj
    0.49
    Kjelder
    0.46
    Portail
    0.44
    }$​
    0.41
     queſta
    0.40
    Portale
    0.40
    хьтан
    0.38
     avulla
    0.38
    AndroidJUnit
    0.37
     jener
    0.36
    Act Density 0.018%

    No Known Activations