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

    Neuronpedia

    INDEX
    Explanations

    words that denote something being difficult, regulated, or against the rules

    oai_token-act-pair · gemini-2.0-flash

    easy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sado
    -0.53
     zwaar
    -0.51
     géant
    -0.50
    rond
    -0.50
    ysmal
    -0.49
     SMG
    -0.49
     myſelf
    -0.49
    jemah
    -0.48
     purpoſe
    -0.47
     jsPsych
    -0.45
    POSITIVE LOGITS
     BorderSide
    0.83
    EClass
    0.72
    MemoryWarning
    0.69
    ManagedBean
    0.68
    SharedCtor
    0.68
    DockStyle
    0.67
    ibatis
    0.66
     BoxFit
    0.65
    testify
    0.65
     onAnimation
    0.63
    Act Density 7.019%

    No Known Activations