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

    Neuronpedia

    INDEX
    Explanations

    sets of objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wholes
    -0.07
     Cat
    -0.07
    _DATABASE
    -0.07
     Vale
    -0.07
    (ci
    -0.07
     factories
    -0.07
    Leading
    -0.07
    -х
    -0.06
    ẹ
    -0.06
     variance
    -0.06
    POSITIVE LOGITS
     srov
    0.06
    нулась
    0.06
    (target
    0.06
     freund
    0.06
     Provided
    0.06
    _PARTITION
    0.06
     did
    0.06
    �
    0.06
    άβ
    0.06
     seeking
    0.05
    Act Density 0.032%

    No Known Activations