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

    Neuronpedia

    INDEX
    Explanations

    die

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ac
    -0.08
     liberals
    -0.07
     Seminar
    -0.07
    ==-
    -0.07
     Tòa
    -0.06
    .matmul
    -0.06
    (reason
    -0.06
    getDisplay
    -0.06
     en
    -0.06
    _connect
    -0.06
    POSITIVE LOGITS
    Sparse
    0.06
     dysfunctional
    0.06
     truncated
    0.06
    _stdio
    0.06
    常
    0.06
    olutely
    0.06
    comes
    0.06
    ::{↵
    0.06
    ทำ
    0.05
     Je
    0.05
    Act Density 0.032%

    No Known Activations