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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mucho
    -0.07
     Defaults
    -0.07
     almonds
    -0.07
     بار
    -0.07
    .toastr
    -0.06
     한국
    -0.06
     crossings
    -0.06
     FRIEND
    -0.06
    =@"
    -0.06
     Cameroon
    -0.06
    POSITIVE LOGITS
     бой
    0.06
    롭
    0.06
    řad
    0.06
    _nan
    0.06
    Rem
    0.06
    歌
    0.06
    _episode
    0.06
     poisoned
    0.06
    製
    0.06
     Molecular
    0.06
    Act Density 0.000%

    No Known Activations