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

    Neuronpedia

    INDEX
    Explanations

    Hide/show transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swan
    -0.07
    (String
    -0.06
     Barry
    -0.06
    POSITORY
    -0.06
     LINE
    -0.06
     simul
    -0.06
     soak
    -0.06
    ('/')[-
    -0.06
    BEST
    -0.06
     tweaking
    -0.06
    POSITIVE LOGITS
    ımda
    0.07
    ่านมา
    0.07
     Feeling
    0.06
    -)
    0.06
    xfe
    0.06
     우
    0.06
    -envelope
    0.06
    -economic
    0.06
    しょう
    0.06
    Cow
    0.06
    Act Density 0.023%

    No Known Activations