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
     against
    -0.06
     takdir
    -0.06
     sequencing
    -0.06
     unprecedented
    -0.06
     faithful
    -0.06
     ارزیابی
    -0.06
    /music
    -0.06
    open
    -0.06
     lay
    -0.06
    aper
    -0.06
    POSITIVE LOGITS
    sq
    0.07
    DESC
    0.07
    鄉
    0.07
     Fury
    0.06
    WT
    0.06
     Plzeň
    0.06
     Greenville
    0.06
    řich
    0.06
     @_
    0.06
    stances
    0.06
    Act Density 0.000%

    No Known Activations