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

    Neuronpedia

    INDEX
    Explanations

    center and edges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    力を
    -0.07
    861
    -0.07
     अगर
    -0.06
    449
    -0.06
    alone
    -0.06
     Marino
    -0.06
    762
    -0.06
    949
    -0.06
     barber
    -0.06
     repr
    -0.06
    POSITIVE LOGITS
     Ми
    0.07
     удов
    0.06
    \Support
    0.06
    ρε
    0.06
    neum
    0.06
    <Cell
    0.06
    阶
    0.06
    дап
    0.06
     theater
    0.06
    WWW
    0.06
    Act Density 0.024%

    No Known Activations