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

    Neuronpedia

    INDEX
    Explanations

    Alger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pop
    -0.07
    ddd
    -0.07
    cee
    -0.07
     crowds
    -0.06
     parks
    -0.06
    friends
    -0.06
    adu
    -0.06
     parade
    -0.06
     TBD
    -0.06
    ood
    -0.06
    POSITIVE LOGITS
     Algeria
    0.11
     Alger
    0.09
    以为
    0.07
     Claude
    0.06
    昭
    0.06
     を
    0.06
     표현
    0.06
    .Wh
    0.06
    =L
    0.06
     đau
    0.06
    Act Density 0.001%

    No Known Activations