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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     škol
    -0.07
    цем
    -0.06
     Inf
    -0.06
    渐
    -0.06
     aggrav
    -0.06
    ream
    -0.06
     кров
    -0.06
     Dong
    -0.06
    oreal
    -0.06
    Rec
    -0.06
    POSITIVE LOGITS
     Bloody
    0.08
     keyboard
    0.07
    就是
    0.07
    ơi
    0.07
     Keyboard
    0.07
    ToolStripMenuItem
    0.07
     empower
    0.07
     Recorder
    0.06
    AN
    0.06
     Barrel
    0.06
    Act Density 0.003%

    No Known Activations