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

    Neuronpedia

    INDEX
    Explanations

    Strong desire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    喤
    -0.07
     במחיר
    -0.07
    >K
    -0.07
     detrimental
    -0.06
     Contractor
    -0.06
    带头
    -0.06
     bath
    -0.06
    (Print
    -0.06
    膽
    -0.06
    odynamics
    -0.06
    POSITIVE LOGITS
    北方
    0.07
     imag
    0.07
     ANSW
    0.07
     NEO
    0.07
     halted
    0.07
     intimate
    0.07
    ningar
    0.07
     forma
    0.07
     intelligence
    0.07
     Angeles
    0.07
    Act Density 0.016%

    No Known Activations