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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical conditions or treatments and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    evaluative language and assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.61
     moll
    -0.47
     ey
    -0.45
    ambo
    -0.45
    المكان
    -0.44
     незавершена
    -0.44
    hallen
    -0.44
    Rüyada
    -0.43
     Firing
    -0.43
    Lau
    -0.42
    POSITIVE LOGITS
    jména
    0.51
     émission
    0.48
     prévention
    0.47
     Versorgung
    0.47
    ambilan
    0.46
    cripciones
    0.45
    )_/¯
    0.44
    zzleHttp
    0.44
     prevención
    0.43
    RegressionTest
    0.43
    Act Density 1.684%

    No Known Activations