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
     американ
    -0.07
    Owners
    -0.06
    _theta
    -0.06
     commits
    -0.06
     grandmother
    -0.06
    gın
    -0.06
    STRUCTOR
    -0.06
    ftype
    -0.06
    した
    -0.06
    "After
    -0.06
    POSITIVE LOGITS
    .exclude
    0.07
    .POS
    0.06
    .organ
    0.06
     Votes
    0.06
     disillusion
    0.06
     πε
    0.06
     LOCK
    0.06
    พอ
    0.06
     böylece
    0.06
     एप
    0.06
    Act Density 0.066%

    No Known Activations