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

    Neuronpedia

    INDEX
    Explanations

    345

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fetch
    -0.07
    Courier
    -0.07
     memes
    -0.06
    orre
    -0.06
     take
    -0.06
     Logan
    -0.06
    Uses
    -0.06
     camps
    -0.06
    '}}>
    -0.06
    icense
    -0.06
    POSITIVE LOGITS
    ंज
    0.06
     financing
    0.06
    ()',
    0.06
    grily
    0.06
    _SPELL
    0.06
     졸업
    0.06
    ermint
    0.06
    \Form
    0.06
    .phi
    0.06
    TECTED
    0.06
    Act Density 0.008%

    No Known Activations