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

    Neuronpedia

    INDEX
    Explanations

    absorb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cafeteria
    -0.07
    )>=
    -0.06
    หร
    -0.06
    _bits
    -0.06
    cta
    -0.06
     practitioner
    -0.06
    .prepare
    -0.06
     generar
    -0.06
    inda
    -0.06
    retorno
    -0.06
    POSITIVE LOGITS
     emotion
    0.07
     afflict
    0.06
     arising
    0.06
    -str
    0.06
    PLEMENT
    0.06
     Orden
    0.06
    rete
    0.06
     representing
    0.06
     yüzde
    0.06
     believable
    0.06
    Act Density 0.010%

    No Known Activations