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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cause
    -0.07
    riting
    -0.07
    CDF
    -0.06
     revenge
    -0.06
     проводить
    -0.06
    kyně
    -0.06
     plans
    -0.06
    几
    -0.06
    语
    -0.06
     beats
    -0.06
    POSITIVE LOGITS
    -flex
    0.06
    nze
    0.06
    apter
    0.06
     negatively
    0.06
     LI
    0.06
     Memory
    0.06
     UTIL
    0.06
     Mime
    0.06
     messed
    0.06
     FontWeight
    0.06
    Act Density 0.006%

    No Known Activations