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

    Neuronpedia

    INDEX
    Explanations

    phrases focusing on self-awareness and emotional struggles

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

    shouldn't or should

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.38
    tics
    -0.37
    contentLoaded
    -0.37
     Sib
    -0.36
    +};
    -0.36
    exels
    -0.36
    Sib
    -0.35
     unknownFields
    -0.35
    sing
    -0.34
    loride
    -0.34
    POSITIVE LOGITS
    GraphicsUnit
    0.58
    didSet
    0.49
    BeginInit
    0.48
     femininos
    0.48
     bendera
    0.47
    SocketAddress
    0.47
     banderas
    0.44
    AddTagHelper
    0.44
    tinyos
    0.42
    EndGlobal
    0.41
    Act Density 0.055%

    No Known Activations