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

    Neuronpedia

    INDEX
    Explanations

    joker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     passive
    -0.09
     mult
    -0.08
     Passenger
    -0.08
     sofrimento
    -0.08
     conflic
    -0.08
    mult
    -0.08
    מח
    -0.07
    Passive
    -0.07
    _MULTI
    -0.07
     passenger
    -0.07
    POSITIVE LOGITS
     মুহ
    0.09
     मौका
    0.08
     সুযোগ
    0.08
     సందర్భంగా
    0.08
    ows
    0.08
    钥
    0.08
     అవకాశ
    0.08
    orto
    0.08
    ICIAL
    0.08
    ås
    0.08
    Act Density 0.003%

    No Known Activations