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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pj
    -0.06
     poetic
    -0.06
     '*
    -0.06
     faults
    -0.06
     avan
    -0.06
    افع
    -0.06
    ')(
    -0.06
     ['#
    -0.06
    prung
    -0.06
    ักด
    -0.06
    POSITIVE LOGITS
     الأرض
    0.07
     دریافت
    0.07
    露
    0.07
     inadvert
    0.06
     searchable
    0.06
    hort
    0.06
    (endpoint
    0.06
     min
    0.06
    _make
    0.06
    Clause
    0.06
    Act Density 0.023%

    No Known Activations