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

    Neuronpedia

    INDEX
    Explanations

    couples going out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (stats
    -0.07
    erokee
    -0.07
     MASK
    -0.07
    ('__
    -0.06
     jets
    -0.06
    alarm
    -0.06
    бот
    -0.06
     Sandy
    -0.06
     CMD
    -0.06
     кир
    -0.06
    POSITIVE LOGITS
    .tp
    0.06
     À
    0.06
    ortic
    0.06
     vyb
    0.06
    �
    0.06
     surround
    0.06
     Marketable
    0.06
     Möglichkeit
    0.06
     ramifications
    0.06
    -､
    0.06
    Act Density 0.075%

    No Known Activations