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

    Neuronpedia

    INDEX
    Explanations

    career

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _From
    -0.07
    group
    -0.07
    .register
    -0.07
    ानव
    -0.06
    Pane
    -0.06
    IOUS
    -0.06
     inject
    -0.06
    據
    -0.06
     cosy
    -0.06
    .spring
    -0.06
    POSITIVE LOGITS
    \Domain
    0.07
    undaki
    0.07
     paradigm
    0.07
    istency
    0.06
    ัศ
    0.06
     ache
    0.06
     العلم
    0.06
     accomplishments
    0.06
    (msg
    0.06
    ЛЬ
    0.06
    Act Density 0.007%

    No Known Activations