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

    Neuronpedia

    INDEX
    Explanations

    Discourse markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tool
    -0.08
     fifo
    -0.07
     entreprise
    -0.07
     mdl
    -0.07
    finger
    -0.06
    beiter
    -0.06
    tasks
    -0.06
     contenders
    -0.06
    PRS
    -0.06
    .reflect
    -0.06
    POSITIVE LOGITS
     dividing
    0.08
    을
    0.07
    .ERR
    0.07
     //=
    0.07
     elseif
    0.07
     chol
    0.06
     melanch
    0.06
    var
    0.06
    "]/
    0.06
    ای
    0.06
    Act Density 0.623%

    No Known Activations