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

    Neuronpedia

    INDEX
    Explanations

    foreign language texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _closure
    -0.07
     forKey
    -0.07
    step
    -0.07
    .singleton
    -0.06
    replace
    -0.06
     Authors
    -0.06
    _var
    -0.06
    fore
    -0.06
    enqueue
    -0.06
    ;\
    -0.06
    POSITIVE LOGITS
    oco
    0.07
     comrades
    0.07
    Xd
    0.06
     pang
    0.06
     vlastně
    0.06
    کاران
    0.06
     Sb
    0.06
     precise
    0.06
     accurate
    0.06
     chiếc
    0.06
    Act Density 0.007%

    No Known Activations