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

    Neuronpedia

    INDEX
    Explanations

    practical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irket
    -0.07
     Feld
    -0.06
     achievement
    -0.06
     Opposition
    -0.06
     Ang
    -0.06
     documentos
    -0.06
    iber
    -0.06
     demi
    -0.06
     Tür
    -0.06
     som
    -0.06
    POSITIVE LOGITS
     dads
    0.07
    shoot
    0.07
     Determine
    0.06
    This
    0.06
    ्ह
    0.06
    �
    0.06
     Hell
    0.06
     daunting
    0.06
    aware
    0.06
    Continue
    0.06
    Act Density 0.014%

    No Known Activations