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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     underground
    -0.07
    vs
    -0.07
     voices
    -0.07
     termination
    -0.07
     exploitation
    -0.07
    V
    -0.07
    $config
    -0.06
     Vari
    -0.06
     annotated
    -0.06
     Waterproof
    -0.06
    POSITIVE LOGITS
    emap
    0.07
     Serialize
    0.06
    ereço
    0.06
    acl
    0.06
     đai
    0.06
    ías
    0.06
    coe
    0.06
    оком
    0.06
    quirrel
    0.06
    weathermap
    0.06
    Act Density 0.013%

    No Known Activations