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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [next
    -0.08
    (lista
    -0.08
    Johnny
    -0.07
     Richardson
    -0.07
    スペース
    -0.07
     condi
    -0.07
    _lab
    -0.07
     zich
    -0.07
     conceptual
    -0.07
     clips
    -0.07
    POSITIVE LOGITS
    value
    0.07
     raising
    0.07
    ꂫ
    0.07
     after
    0.07
     paid
    0.07
    0.07
    ished
    0.07
    룃
    0.07
    utions
    0.07
    챃
    0.07
    Act Density 0.001%

    No Known Activations