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

    Neuronpedia

    INDEX
    Explanations

    code/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lights
    -0.07
     теперь
    -0.07
    .setStroke
    -0.07
     accommodate
    -0.07
    긔
    -0.07
     cover
    -0.07
     fatt
    -0.06
    новаж
    -0.06
    errmsg
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     das
    0.06
     случае
    0.06
    __(
    0.06
    471
    0.06
    	tp
    0.06
    Ay
    0.06
    Conditional
    0.06
     indefinite
    0.06
     Chaos
    0.06
    ))^
    0.06
    Act Density 0.000%

    No Known Activations