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

    Neuronpedia

    INDEX
    Explanations

    comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amins
    -0.07
    ेष
    -0.06
    stanbul
    -0.06
    อว
    -0.06
     believers
    -0.06
    �
    -0.06
     attenu
    -0.06
    ственная
    -0.06
    abbreviation
    -0.06
     extortion
    -0.06
    POSITIVE LOGITS
    .sig
    0.07
     renting
    0.07
     chopping
    0.07
     Siege
    0.06
     구매
    0.06
     Dana
    0.06
    izik
    0.06
     노래
    0.06
    <Transaction
    0.06
     Smith
    0.06
    Act Density 0.000%

    No Known Activations