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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admirable
    -0.06
    
    -0.06
    より
    -0.06
     rigor
    -0.06
    _deleted
    -0.06
     нагруз
    -0.06
     ви
    -0.06
    irteen
    -0.06
    兵
    -0.06
    інки
    -0.06
    POSITIVE LOGITS
     assass
    0.07
    ))?
    0.07
    ='';↵
    0.07
    .unshift
    0.07
    .aw
    0.07
     počet
    0.07
     kon
    0.06
    (dummy
    0.06
     ชนะ
    0.06
     ecstatic
    0.06
    Act Density 0.000%

    No Known Activations