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

    Neuronpedia

    INDEX
    Explanations

    pp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ém
    -0.07
    ól
    -0.07
    �
    -0.07
     nam
    -0.07
    roz
    -0.07
    emplates
    -0.06
     improbable
    -0.06
    hl
    -0.06
    fos
    -0.06
    mes
    -0.06
    POSITIVE LOGITS
     Adidas
    0.08
     bailout
    0.07
     Talking
    0.07
    .TIME
    0.07
     wheelchair
    0.07
     hải
    0.07
    ��
    0.07
     offsets
    0.07
    財
    0.07
    哌
    0.06
    Act Density 0.000%

    No Known Activations