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

    Neuronpedia

    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posal
    -0.08
    (stdout
    -0.08
     grads
    -0.08
    �
    -0.07
    .compat
    -0.07
    ients
    -0.07
    Prim
    -0.07
    posals
    -0.07
     iste
    -0.07
     stdout
    -0.07
    POSITIVE LOGITS
     entities
    0.11
    现实
    0.10
     métier
    0.10
     현실
    0.09
     modeled
    0.09
     phenomena
    0.09
     modeling
    0.09
     Modeling
    0.08
     métiers
    0.08
    _entities
    0.08
    Act Density 0.025%

    No Known Activations