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

    Neuronpedia

    INDEX
    Explanations

    learn something new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Balfour
    0.50
     Sheets
    0.46
     `#
    0.42
     respuesta
    0.40
     replying
    0.40
     reply
    0.39
     Balk
    0.39
     Bain
    0.39
     REPLY
    0.39
     Lists
    0.39
    POSITIVE LOGITS
    wtf
    0.42
    Wh
    0.40
     ix
    0.39
    Digest
    0.38
    wh
    0.38
    zip
    0.38
    witch
    0.37
     wy
    0.37
     თ
    0.37
    varphi
    0.37
    Act Density 0.000%

    No Known Activations