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

    Neuronpedia

    INDEX
    Explanations

    /uploads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     constantly
    -0.07
    �
    -0.07
    Witness
    -0.06
     лік
    -0.06
    らの
    -0.06
    .parallel
    -0.06
    (predictions
    -0.06
     Mongolia
    -0.06
    findAll
    -0.06
    ูช
    -0.06
    POSITIVE LOGITS
    /uploads
    0.19
     вед
    0.11
    /svg
    0.11
    uploads
    0.07
     Engineering
    0.07
    etrics
    0.07
    EndInit
    0.07
     Clarkson
    0.07
    Passwords
    0.07
     activates
    0.07
    Act Density 0.004%

    No Known Activations