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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    อส
    -0.07
    elper
    -0.07
     Idol
    -0.06
    ällt
    -0.06
     Latin
    -0.06
    _provider
    -0.06
     Parser
    -0.06
    igmoid
    -0.06
    .boost
    -0.06
     광
    -0.06
    POSITIVE LOGITS
     Fund
    0.07
     find
    0.07
     identify
    0.06
    线
    0.06
     discover
    0.06
     PIN
    0.06
    ABCDE
    0.06
     된다
    0.06
     　 　 　 　 　 　 　 　
    0.06
     discovered
    0.06
    Act Density 0.031%

    No Known Activations