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

    Neuronpedia

    INDEX
    Explanations

    add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /app
    -0.06
     рав
    -0.06
    _traj
    -0.06
     triumph
    -0.06
    Clinton
    -0.06
    marshal
    -0.06
     зал
    -0.06
    ่เป
    -0.06
    Smith
    -0.06
    ştır
    -0.06
    POSITIVE LOGITS
     adding
    0.10
     added
    0.09
    Adding
    0.09
     adds
    0.07
    .addView
    0.07
     слож
    0.07
     add
    0.07
    合わせ
    0.07
    ):
↵
↵
    0.06
     seri
    0.06
    Act Density 0.029%

    No Known Activations