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

    Neuronpedia

    INDEX
    Explanations

    Code, configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Birds
    -0.08
    (grad
    -0.07
    ɵ
    -0.07
     manžel
    -0.07
    thora
    -0.06
    인지
    -0.06
    pute
    -0.06
    -builder
    -0.06
     hashtags
    -0.06
    precated
    -0.06
    POSITIVE LOGITS
    consult
    0.07
     Sai
    0.07
     tofu
    0.06
    ｉ
    0.06
    imest
    0.06
     відбува
    0.06
    ademic
    0.06
    .mass
    0.06
    Personally
    0.06
    abel
    0.06
    Act Density 0.008%

    No Known Activations