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

    Neuronpedia

    INDEX
    Explanations

    Word fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obs
    -0.06
    .compose
    -0.06
    Lots
    -0.06
    "M
    -0.06
    付け
    -0.06
     puppies
    -0.06
     القدم
    -0.06
    _AUDIO
    -0.06
    岳
    -0.06
    thesis
    -0.06
    POSITIVE LOGITS
     medial
    0.07
    .Length
    0.07
     önüne
    0.06
     tehdy
    0.06
     nationalist
    0.06
    _trap
    0.06
     пре
    0.06
    .Generated
    0.06
     ballots
    0.06
    ΄
    0.06
    Act Density 0.005%

    No Known Activations