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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STOP
    -0.08
     Kramer
    -0.07
     ''}↵
    -0.07
    <Cell
    -0.07
    団
    -0.07
     Braun
    -0.07
    ")(
    -0.07
    "](
    -0.07
     suiv
    -0.07
     rip
    -0.06
    POSITIVE LOGITS
    owych
    0.07
    ,
    0.07
     saddle
    0.06
    CHANT
    0.06
    Lo
    0.06
     cliente
    0.06
     Lo
    0.06
    agine
    0.06
    (labels
    0.06
    okes
    0.06
    Act Density 0.008%

    No Known Activations