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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loch
    -0.07
    unifu
    -0.07
    「あ
    -0.06
     лишь
    -0.06
     Bru
    -0.06
    成为
    -0.06
     barracks
    -0.06
     suffer
    -0.06
     �
    -0.06
     gra
    -0.06
    POSITIVE LOGITS
    hone
    0.07
     getAddress
    0.07
    ates
    0.07
    EO
    0.07
     Arthropoda
    0.06
    (coeffs
    0.06
    ''↵
    0.06
    _tE
    0.06
    axis
    0.06
    Who
    0.06
    Act Density 0.020%

    No Known Activations