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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ArrayList
    -0.07
    _ix
    -0.07
    (S
    -0.06
     gameObject
    -0.06
    Brun
    -0.06
    ,e
    -0.06
    _goto
    -0.06
    **************
    -0.06
    ortality
    -0.06
     b
    -0.06
    POSITIVE LOGITS
     foreign
    0.08
    Particles
    0.07
     Foreign
    0.07
     cms
    0.06
    299
    0.06
     unnatural
    0.06
    лях
    0.06
    atra
    0.06
     undermine
    0.06
    [df
    0.06
    Act Density 0.004%

    No Known Activations