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

    Neuronpedia

    INDEX
    Explanations

    sorted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMATE
    -0.07
    qb
    -0.07
    SKIP
    -0.07
    998
    -0.07
    +z
    -0.07
     DISTRIBUT
    -0.07
    _GATE
    -0.06
    .fetch
    -0.06
     ось
    -0.06
    EObject
    -0.06
    POSITIVE LOGITS
     बत
    0.07
     aging
    0.06
    лых
    0.06
     Reform
    0.06
     moving
    0.06
    _region
    0.06
    acing
    0.06
     reasoning
    0.06
     living
    0.06
     για
    0.06
    Act Density 0.000%

    No Known Activations