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

    Neuronpedia

    INDEX
    Explanations

    is available

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :{
    -0.06
    ежать
    -0.06
    ｰ
    -0.06
     bru
    -0.06
    _dims
    -0.06
    -roll
    -0.06
    肩
    -0.06
     recess
    -0.06
     bet
    -0.06
    _subject
    -0.06
    POSITIVE LOGITS
    erli
    0.07
     üy
    0.06
     WS
    0.06
     OrderedDict
    0.06
    으나
    0.06
     spécial
    0.06
    ิถ
    0.06
     currency
    0.06
     existential
    0.06
    ')");↵
    0.06
    Act Density 0.003%

    No Known Activations