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

    Neuronpedia

    INDEX
    Explanations

    government actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rat
    -0.07
     resultat
    -0.06
     slowing
    -0.06
     lit
    -0.06
     Continued
    -0.06
     torture
    -0.06
     relied
    -0.06
    @Bean
    -0.06
     donna
    -0.06
     Nina
    -0.06
    POSITIVE LOGITS
     Finished
    0.06
    ��
    0.06
    chunks
    0.06
    _JOB
    0.06
    ")),
    0.06
    ималь
    0.06
     Sessions
    0.06
    _constants
    0.06
    namen
    0.06
    rsp
    0.06
    Act Density 0.016%

    No Known Activations