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

    Neuronpedia

    INDEX
    Explanations

    retention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cached
    -0.06
     convict
    -0.06
     BRAND
    -0.06
    अ
    -0.06
     Phạm
    -0.06
     CHRIST
    -0.06
    オリ
    -0.06
     зим
    -0.06
     Sew
    -0.06
    гляд
    -0.06
    POSITIVE LOGITS
    urally
    0.07
    ‐'
    0.07
    -j
    0.07
     ranch
    0.06
    _cut
    0.06
    _detection
    0.06
     Moz
    0.06
     lu
    0.06
    (ic
    0.06
    (go
    0.06
    Act Density 0.000%

    No Known Activations