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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dale
    -0.07
     Altern
    -0.06
     suicidal
    -0.06
    .isAdmin
    -0.06
     링
    -0.06
     adjacency
    -0.06
    .BAD
    -0.06
    дат
    -0.06
    atrigesimal
    -0.06
     destiny
    -0.06
    POSITIVE LOGITS
    _IMAGES
    0.07
    ober
    0.07
    ，↵
    0.07
     góp
    0.07
    ۲۰۱
    0.07
     tracks
    0.06
     exclusively
    0.06
     printed
    0.06
     zprac
    0.06
     ως
    0.06
    Act Density 0.002%

    No Known Activations