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

    Neuronpedia

    INDEX
    Explanations

    Disappearing, fading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plement
    -0.08
    不上
    -0.08
     �
    -0.07
    бор
    -0.07
    ład
    -0.07
     �
    -0.07
    elif
    -0.07
     servo
    -0.07
     官
    -0.07
     rob
    -0.07
    POSITIVE LOGITS
    掉
    0.13
     fog
    0.10
    Fog
    0.09
    消
    0.09
     dissol
    0.08
     Fog
    0.08
     dissolve
    0.08
     remnants
    0.08
    灭
    0.08
     grasa
    0.08
    Act Density 0.027%

    No Known Activations