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

    Neuronpedia

    INDEX
    Explanations

    computer security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hoc
    -0.08
     destinado
    -0.08
    ును
    -0.08
     추진
    -0.08
     Voraussetzungen
    -0.08
    brecht
    -0.08
    manageable
    -0.08
     przedsi
    -0.08
    bergement
    -0.07
     vooruit
    -0.07
    POSITIVE LOGITS
     disagree
    0.14
     disag
    0.12
     agree
    0.11
     agreeing
    0.11
    意见
    0.11
     agrees
    0.10
     authoritative
    0.10
     disagreement
    0.10
    认为
    0.10
     reputable
    0.10
    Act Density 0.102%

    No Known Activations