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

    Neuronpedia

    INDEX
    Explanations

    presumably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Singer
    -0.07
     wants
    -0.06
     "")
    -0.06
    Water
    -0.06
    禁止
    -0.06
     destroyed
    -0.06
     separator
    -0.06
     ""↵
    -0.06
    .toolbar
    -0.06
    Profit
    -0.06
    POSITIVE LOGITS
     presumably
    0.16
    umably
    0.12
     presume
    0.11
     presum
    0.09
     presumption
    0.09
     supposedly
    0.09
     presumed
    0.08
    情報
    0.08
    sembling
    0.08
    ución
    0.07
    Act Density 0.002%

    No Known Activations