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

    Neuronpedia

    INDEX
    Explanations

    Exaggeration and intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瓣
    -0.08
     kinds
    -0.08
     pesc
    -0.08
    .kind
    -0.08
    woo
    -0.08
     uitspraak
    -0.08
    Hat
    -0.07
    awai
    -0.07
     lecturers
    -0.07
    Lect
    -0.07
    POSITIVE LOGITS
     গুরু
    0.10
     unacceptable
    0.10
     absurd
    0.09
     scream
    0.09
     serious
    0.09
     tragedy
    0.09
    SAM
    0.09
     desconoc
    0.09
     downright
    0.09
     bizarre
    0.09
    Act Density 0.038%

    No Known Activations