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

    Neuronpedia

    INDEX
    Explanations

    Remainder calculation problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ominous
    -0.07
    Individual
    -0.07
     Obtain
    -0.07
    Univers
    -0.07
     erratic
    -0.07
     ActionBar
    -0.07
    .friends
    -0.07
    🦋
    -0.07
    viders
    -0.06
    🏎
    -0.06
    POSITIVE LOGITS
    调剂
    0.07
    _case
    0.07
    救助
    0.07
    .save
    0.07
    _match
    0.07
     CITY
    0.06
    fu
    0.06
    _pe
    0.06
    .Sequence
    0.06
    본
    0.06
    Act Density 0.023%

    No Known Activations