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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [-
    -0.07
     overcrow
    -0.07
    weigh
    -0.06
    ски
    -0.06
     controlled
    -0.06
     Initialized
    -0.06
     alcohol
    -0.06
     proto
    -0.06
    ục
    -0.06
     Lawyers
    -0.06
    POSITIVE LOGITS
    issenschaft
    0.06
     ポ
    0.06
    ohn
    0.06
     francouz
    0.06
    essions
    0.06
    Modern
    0.06
     verbess
    0.06
    .getResources
    0.06
    parentId
    0.06
    äß
    0.06
    Act Density 0.000%

    No Known Activations