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

    Neuronpedia

    INDEX
    Explanations

    P

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    optgroup
    -0.07
     Ih
    -0.06
    �
    -0.06
     Halifax
    -0.06
    omitempty
    -0.06
    Minimal
    -0.06
     tud
    -0.06
     leftist
    -0.06
     bustling
    -0.06
    .Detail
    -0.06
    POSITIVE LOGITS
     investigates
    0.07
     */
↵
↵
↵
    0.07
    أن
    0.06
    _lstm
    0.06
    া�
    0.06
    _A
    0.06
     Heb
    0.06
    ented
    0.06
    _C
    0.06
    الك
    0.06
    Act Density 0.032%

    No Known Activations