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

    Neuronpedia

    INDEX
    Explanations

    count

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     распрост
    -0.07
     bisc
    -0.07
    感情
    -0.06
    "Now
    -0.06
    _DISK
    -0.06
     Invite
    -0.06
    vehicle
    -0.06
    Modification
    -0.06
    -faced
    -0.06
     animals
    -0.06
    POSITIVE LOGITS
     boo
    0.07
     Stunden
    0.06
    .assertIsNot
    0.06
    온
    0.06
    cbd
    0.06
     sistema
    0.06
     («
    0.06
     contato
    0.06
    ภ
    0.06
    ,it
    0.06
    Act Density 0.000%

    No Known Activations