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

    Neuronpedia

    INDEX
    Explanations

    attachment theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _attention
    -0.07
    šel
    -0.07
    _conv
    -0.07
    оды
    -0.06
     символ
    -0.06
     Decompiled
    -0.06
    ())/
    -0.06
    .Str
    -0.06
    íveis
    -0.06
    _matrices
    -0.06
    POSITIVE LOGITS
     creation
    0.07
    ........................
    0.06
    _cost
    0.06
     dost
    0.06
    .stage
    0.06
     undert
    0.06
     sb
    0.06
    ................................
    0.06
     LOAD
    0.06
     got
    0.06
    Act Density 0.025%

    No Known Activations