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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     　 　 　 　 　
    -0.07
     навк
    -0.07
     recordings
    -0.06
    ıldı
    -0.06
    至
    -0.06
     distortion
    -0.06
     implicated
    -0.06
     
    -0.06
    .↵
    -0.06
     ebenfalls
    -0.06
    POSITIVE LOGITS
    polator
    0.07
     dess
    0.06
    >D
    0.06
    -doc
    0.06
     rooft
    0.06
     hundreds
    0.06
    →→
    0.06
    ymoon
    0.06
     disproportionate
    0.06
    еди
    0.06
    Act Density 0.286%

    No Known Activations