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

    Neuronpedia

    INDEX
    Explanations

    Sex differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lego
    -0.07
    .writ
    -0.07
     Exit
    -0.07
     ona
    -0.07
    edla
    -0.06
     posición
    -0.06
     noci
    -0.06
     ApplicationRecord
    -0.06
     taper
    -0.06
    GitHub
    -0.06
    POSITIVE LOGITS
     sessionId
    0.07
    Mt
    0.06
     meaningless
    0.06
    andin
    0.06
     BEN
    0.06
     사건
    0.06
    ashes
    0.05
    ="<?=
    0.05
    eyer
    0.05
    MISSION
    0.05
    Act Density 0.113%

    No Known Activations