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

    Neuronpedia

    INDEX
    Explanations

    Forum posts/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confessed
    -0.07
     obvious
    -0.07
     slander
    -0.07
     dressing
    -0.07
    abeth
    -0.07
     Armstrong
    -0.07
     Johann
    -0.06
    (jQuery
    -0.06
    캥
    -0.06
    emann
    -0.06
    POSITIVE LOGITS
    Tuple
    0.07
     layer
    0.07
    {};↵
    0.07
    layers
    0.07
    shared
    0.07
     Fn
    0.07
    ThanOr
    0.07
     entity
    0.06
     IsPlainOldData
    0.06
    人际
    0.06
    Act Density 0.106%

    No Known Activations