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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roads
    -0.07
    亮
    -0.07
    EOS
    -0.07
     Dome
    -0.07
     самый
    -0.06
    los
    -0.06
    three
    -0.06
    ん
    -0.06
     hospital
    -0.06
     cloth
    -0.06
    POSITIVE LOGITS
    PROPERTY
    0.06
    _REV
    0.06
    (tv
    0.06
     stringByAppendingString
    0.06
    기술
    0.06
     teknik
    0.06
    ıyorum
    0.06
    QUENCY
    0.06
    .chat
    0.06
    _pars
    0.06
    Act Density 0.011%

    No Known Activations