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

    Neuronpedia

    INDEX
    Explanations

    <>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frightened
    -0.07
    .=
    -0.07
     mop
    -0.07
     swinger
    -0.07
    .Clear
    -0.06
    ross
    -0.06
    .direct
    -0.06
    čas
    -0.06
     Campo
    -0.06
    _phase
    -0.06
    POSITIVE LOGITS
     dovol
    0.07
     '''↵↵
    0.06
    TeV
    0.06
     prefixed
    0.06
    .↵↵↵↵
    0.06
     Older
    0.06
     vend
    0.06
     appro
    0.06
     undermin
    0.06
    >());↵
    0.06
    Act Density 0.000%

    No Known Activations