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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adem
    -0.06
     chast
    -0.06
    adi
    -0.06
    mans
    -0.06
    حم
    -0.05
    locked
    -0.05
    、「
    -0.05
    _stub
    -0.05
     cooper
    -0.05
    (bucket
    -0.05
    POSITIVE LOGITS
    Growing
    0.08
     strugg
    0.07
    toa
    0.07
    게시
    0.07
     swinger
    0.07
     C
    0.07
     leap
    0.07
    pg
    0.07
    greater
    0.07
     icmp
    0.07
    Act Density 0.000%

    No Known Activations