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

    Neuronpedia

    INDEX
    Explanations

    memorable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gebra
    -0.07
    uce
    -0.06
     війни
    -0.06
     Duch
    -0.06
    urdy
    -0.06
    ку
    -0.06
     contradiction
    -0.06
    cdb
    -0.06
    jiang
    -0.06
     BehaviorSubject
    -0.06
    POSITIVE LOGITS
     memorable
    0.14
     nghỉ
    0.07
    forgettable
    0.07
     تنها
    0.07
     неиз
    0.06
    ワー
    0.06
    _->
    0.06
     denim
    0.06
     Vak
    0.06
     alunos
    0.06
    Act Density 0.016%

    No Known Activations