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

    Neuronpedia

    INDEX
    Explanations

    Formulaic/mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _eval
    -0.07
    /session
    -0.06
    �
    -0.06
    ;;;;;;;;
    -0.06
    .Nullable
    -0.06
     Scheduled
    -0.06
    *",
    -0.06
    OCUMENT
    -0.06
     býval
    -0.06
     demise
    -0.06
    POSITIVE LOGITS
     جنگ
    0.07
    Dos
    0.07
     Bristol
    0.07
    Amazing
    0.06
     دل
    0.06
    Dis
    0.06
     ad
    0.06
     empir
    0.06
     warming
    0.06
    QUIRED
    0.06
    Act Density 0.000%

    No Known Activations