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

    Neuronpedia

    INDEX
    Explanations

    cd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pochop
    -0.07
    ].[
    -0.07
    幸
    -0.07
     registrazione
    -0.07
    hint
    -0.07
    infos
    -0.07
    售
    -0.07
    џџџџ
    -0.07
    ريس
    -0.07
    endforeach
    -0.07
    POSITIVE LOGITS
    CD
    0.07
    Stay
    0.07
     kidney
    0.07
     CD
    0.06
    _dim
    0.06
    ัสด
    0.06
     shoved
    0.06
     insulation
    0.06
    (world
    0.06
     LED
    0.05
    Act Density 0.001%

    No Known Activations