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

    Neuronpedia

    INDEX
    Explanations

    negations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     investigation
    -0.07
     Canadians
    -0.07
    _student
    -0.07
     Extras
    -0.06
     displayName
    -0.06
     가정
    -0.06
    Sessions
    -0.06
    ουμε
    -0.06
    教育
    -0.06
     Transmission
    -0.06
    POSITIVE LOGITS
    �
    0.06
    _tr
    0.06
    �
    0.06
    .file
    0.06
    django
    0.06
     Thanksgiving
    0.06
    .sent
    0.06
    airro
    0.06
    ность
    0.06
    सल
    0.06
    Act Density 0.110%

    No Known Activations