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

    Neuronpedia

    INDEX
    Explanations

    code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cope
    -0.07
    워
    -0.06
     irresponsible
    -0.06
     powerhouse
    -0.06
    .guna
    -0.06
    uni
    -0.06
    _die
    -0.06
    ashi
    -0.06
    顾
    -0.06
     erf
    -0.06
    POSITIVE LOGITS
    >.
    0.07
    .Primary
    0.06
    Resource
    0.06
    [Boolean
    0.06
    >Select
    0.06
     Plasma
    0.06
    >[]
    0.06
    RAND
    0.06
    !
↵
    0.06
     teb
    0.06
    Act Density 0.022%

    No Known Activations