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

    Neuronpedia

    INDEX
    Explanations

    Southern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <u
    -0.06
     serr
    -0.06
     marching
    -0.06
     válido
    -0.06
     hh
    -0.06
    uhn
    -0.06
     دن
    -0.06
    vání
    -0.06
     Kut
    -0.06
     рів
    -0.06
    POSITIVE LOGITS
     cyst
    0.07
     жиз
    0.07
    Disposed
    0.07
    itespace
    0.06
    шая
    0.06
    _BEGIN
    0.06
     refrain
    0.06
    Steel
    0.06
     prompted
    0.06
    ount
    0.06
    Act Density 0.142%

    No Known Activations