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

    Neuronpedia

    INDEX
    Explanations

    configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apartments
    -0.07
     är
    -0.07
     Nights
    -0.07
     وقت
    -0.06
    Anything
    -0.06
    ipro
    -0.06
    形式
    -0.06
     цель
    -0.06
     shitty
    -0.06
    kw
    -0.06
    POSITIVE LOGITS
    _APB
    0.06
     neu
    0.06
    )();↵
    0.06
     mContext
    0.06
     endeavor
    0.06
     мил
    0.06
     ctxt
    0.06
    WithURL
    0.06
    Segment
    0.06
    _foreign
    0.06
    Act Density 0.000%

    No Known Activations