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

    Neuronpedia

    INDEX
    Explanations

    modeldjango models and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icked
    0.41
    opra
    0.41
    lee
    0.40
     जंगली
    0.40
    into
    0.39
    cost
    0.39
    fore
    0.38
    Provision
    0.38
    cu
    0.38
    CU
    0.37
    POSITIVE LOGITS
     checkpoints
    0.40
    벼
    0.40
     hypersurfaces
    0.39
     hubs
    0.38
    adiene
    0.38
     Compounds
    0.38
     idioms
    0.38
     Dimensions
    0.37
     appendages
    0.37
     equalities
    0.37
    Act Density 0.000%

    No Known Activations