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

    Neuronpedia

    INDEX
    Explanations

    Surveys and questionnaires

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flow
    -0.08
    viously
    -0.07
    iou
    -0.07
    BODY
    -0.07
    ädchen
    -0.07
     indications
    -0.07
    dda
    -0.07
    CREASE
    -0.07
    inski
    -0.07
    _BODY
    -0.07
    POSITIVE LOGITS
     rs
    0.07
     UserRole
    0.06
    �
    0.06
    (rs
    0.06
     PRES
    0.05
     -*-↵↵
    0.05
     Garten
    0.05
    assen
    0.05
     Assass
    0.05
    菜
    0.05
    Act Density 0.015%

    No Known Activations