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

    Neuronpedia

    INDEX
    Explanations

    desires and choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bereich
    -0.08
    If
    -0.08
     rire
    -0.08
    Generic
    -0.07
    chein
    -0.07
     GE
    -0.07
    gna
    -0.07
     Generic
    -0.07
    wurf
    -0.07
     Gi
    -0.07
    POSITIVE LOGITS
     원하는
    0.12
     gewenste
    0.12
     istedi
    0.11
     desired
    0.11
     scegli
    0.10
     gewünsch
    0.10
     तय
    0.10
     इच्छ
    0.10
     dictates
    0.10
     jederzeit
    0.10
    Act Density 0.110%

    No Known Activations