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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HT
    -0.07
     imperative
    -0.07
    Compound
    -0.06
     ethn
    -0.06
     न
    -0.06
    mean
    -0.06
     blonde
    -0.06
    statuses
    -0.06
     pagination
    -0.06
     afternoon
    -0.06
    POSITIVE LOGITS
     earns
    0.06
     إلا
    0.06
    _serialize
    0.06
     qualify
    0.06
     spoilers
    0.06
    .Raise
    0.06
     रह
    0.06
    VEN
    0.06
    .learning
    0.06
     Credit
    0.06
    Act Density 0.065%

    No Known Activations