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

    Neuronpedia

    INDEX
    Explanations

    replen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _external
    -0.07
     quiere
    -0.07
    Recursive
    -0.07
     racism
    -0.06
     awkward
    -0.06
     Foo
    -0.06
    (src
    -0.06
     기자
    -0.06
     cars
    -0.06
    っている
    -0.06
    POSITIVE LOGITS
     depleted
    0.08
     P
    0.08
     depletion
    0.07
    .Tween
    0.07
    RESH
    0.07
     replen
    0.07
    Dep
    0.07
     N
    0.07
    ncy
    0.07
    FP
    0.06
    Act Density 0.006%

    No Known Activations