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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marginal
    -0.07
    由
    -0.06
     sang
    -0.06
    Dod
    -0.06
    	current
    -0.06
     écrit
    -0.06
     rents
    -0.06
     plotted
    -0.06
     SetValue
    -0.06
    nested
    -0.06
    POSITIVE LOGITS
     ROOM
    0.07
    ̣
    0.06
    ARDS
    0.06
    AIN
    0.06
    VERIFY
    0.06
    ards
    0.06
    _WEAPON
    0.06
    .Ş
    0.06
    들의
    0.06
    unal
    0.06
    Act Density 0.092%

    No Known Activations