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

    Neuronpedia

    INDEX
    Explanations

    program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    較
    -0.08
     FOOT
    -0.07
    -bit
    -0.07
     fontWeight
    -0.07
    温
    -0.07
    _EQUAL
    -0.07
    なん
    -0.07
    适
    -0.07
     이제
    -0.06
    基
    -0.06
    POSITIVE LOGITS
    transforms
    0.07
    ircraft
    0.06
    исс
    0.06
    .song
    0.06
    corner
    0.06
     spacecraft
    0.06
     Goddess
    0.06
    llum
    0.06
    essenger
    0.06
    credited
    0.06
    Act Density 0.262%

    No Known Activations