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

    Neuronpedia

    INDEX
    Explanations

    Keep your word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     segregation
    -0.08
     unsure
    -0.08
     unknown
    -0.08
    "os
    -0.08
    unknown
    -0.08
    ostat
    -0.08
     Olympus
    -0.07
    _obs
    -0.07
    Poz
    -0.07
     nuclei
    -0.07
    POSITIVE LOGITS
    兑现
    0.16
     obligations
    0.14
     commitments
    0.12
     obligation
    0.12
     obligaciones
    0.10
     promises
    0.10
     incum
    0.10
     Oblig
    0.10
     obligated
    0.10
    履
    0.09
    Act Density 0.051%

    No Known Activations