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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     picnic
    -0.07
     Uno
    -0.06
    _magic
    -0.06
     지역
    -0.06
     drilled
    -0.06
    .two
    -0.06
    blend
    -0.06
    nh
    -0.06
     yeast
    -0.06
    .rad
    -0.06
    POSITIVE LOGITS
     Havana
    0.07
    限
    0.07
    および
    0.07
    طال
    0.07
     Commentary
    0.07
     reiterated
    0.06
     SUS
    0.06
    approval
    0.06
    RARY
    0.06
    rippling
    0.06
    Act Density 0.026%

    No Known Activations