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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﱔ
    -0.07
    .KeyChar
    -0.07
    nbsp
    -0.06
     noble
    -0.06
    очный
    -0.06
    .goal
    -0.06
    AREST
    -0.06
    となる
    -0.06
     kako
    -0.06
    𫄸
    -0.06
    POSITIVE LOGITS
     Nine
    0.07
    signIn
    0.07
     Pastor
    0.07
     dismay
    0.07
    runtime
    0.07
    cname
    0.07
    Installed
    0.07
    �
    0.07
    Maria
    0.07
    cheme
    0.06
    Act Density 0.001%

    No Known Activations