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

    Neuronpedia

    INDEX
    Explanations

    film

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Meat
    -0.07
     Holly
    -0.07
    ображ
    -0.06
    >')
    -0.06
     
    -0.06
    )[-
    -0.06
    nota
    -0.06
     Nir
    -0.06
    -bind
    -0.06
    _internal
    -0.06
    POSITIVE LOGITS
     vill
    0.06
     الشيخ
    0.06
     magnesium
    0.06
     محافظ
    0.06
    Mt
    0.06
     बह
    0.06
    صال
    0.06
     dragged
    0.06
    oxide
    0.06
    utzer
    0.06
    Act Density 0.000%

    No Known Activations