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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    def
    -0.07
    itor
    -0.07
     Might
    -0.07
    Decision
    -0.06
    continuous
    -0.06
     Hey
    -0.06
    .dao
    -0.06
     compressed
    -0.06
     criticised
    -0.06
    peated
    -0.06
    POSITIVE LOGITS
     seat
    0.07
     Seb
    0.07
    coli
    0.07
     acab
    0.06
    inalg
    0.06
     Product
    0.06
     tabIndex
    0.06
    733
    0.06
     erre
    0.06
     �
    0.06
    Act Density 0.017%

    No Known Activations