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

    Neuronpedia

    INDEX
    Explanations

    biased

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    혼
    -0.06
    (Schedulers
    -0.06
    _mock
    -0.06
    ('/')
    -0.06
    	CHECK
    -0.06
    чин
    -0.06
     mentoring
    -0.06
    <fieldset
    -0.06
    Models
    -0.06
    lox
    -0.06
    POSITIVE LOGITS
     loaded
    0.07
     переш
    0.07
     đưa
    0.07
    .bold
    0.07
     contaminated
    0.07
     вплив
    0.07
     ،
    0.06
     balanced
    0.06
    .bool
    0.06
     bên
    0.06
    Act Density 0.010%

    No Known Activations