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

    Neuronpedia

    INDEX
    Explanations

    code and links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $params
    -0.08
    reibt
    -0.08
    params
    -0.08
    (params
    -0.08
     params
    -0.08
     Bennett
    -0.08
     מינ
    -0.07
    nun
    -0.07
    �
    -0.07
    向
    -0.07
    POSITIVE LOGITS
     dit
    0.08
     zapew
    0.07
     nutshell
    0.07
    .github
    0.07
    ikes
    0.07
    dit
    0.07
     Merr
    0.07
     Pirate
    0.06
     обеспечения
    0.06
     guest
    0.06
    Act Density 0.005%

    No Known Activations