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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sigma
    -0.07
     questa
    -0.07
    |"
    -0.07
     schvál
    -0.06
    extends
    -0.06
     `}↵
    -0.06
    "';↵
    -0.06
    $I
    -0.06
    amanho
    -0.06
    ##↵
    -0.06
    POSITIVE LOGITS
    _ids
    0.06
    AGR
    0.06
    とか
    0.06
    _detach
    0.06
     facility
    0.06
     keen
    0.06
     ten
    0.06
     sorts
    0.06
    (float
    0.06
    -text
    0.06
    Act Density 0.006%

    No Known Activations