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

    Neuronpedia

    INDEX
    Explanations

    part of a text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deposits
    -0.07
     attributable
    -0.07
    �
    -0.06
     concluding
    -0.06
     IDD
    -0.06
     Uph
    -0.06
    /pre
    -0.06
     Prize
    -0.06
    VILLE
    -0.06
     retval
    -0.06
    POSITIVE LOGITS
     경험
    0.07
     itertools
    0.06
    ASTE
    0.06
     Д
    0.06
    いの
    0.06
    ientos
    0.06
    ron
    0.06
    conte
    0.06
    RLF
    0.06
    my
    0.06
    Act Density 0.025%

    No Known Activations