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

    Neuronpedia

    INDEX
    Explanations

    research interventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alpha
    -0.07
    hydr
    -0.07
     pronunciation
    -0.07
    ynos
    -0.07
    eta
    -0.07
    _endian
    -0.06
    .primary
    -0.06
    Insets
    -0.06
    _sg
    -0.06
    570
    -0.06
    POSITIVE LOGITS
    ">${
    0.07
    کنان
    0.06
     diy
    0.06
     botanical
    0.06
     Traverse
    0.06
    (dim
    0.06
     đá
    0.06
    uální
    0.06
     EAR
    0.06
     muslim
    0.06
    Act Density 0.053%

    No Known Activations