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

    Neuronpedia

    INDEX
    Explanations

    Frost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swung
    -0.07
    	unsigned
    -0.06
     joven
    -0.06
     Durham
    -0.06
     mujeres
    -0.06
     molecule
    -0.06
     struggled
    -0.06
     Casey
    -0.06
    忙
    -0.06
     hızla
    -0.06
    POSITIVE LOGITS
     Frost
    0.08
     外部
    0.07
    ญ
    0.07
     frost
    0.07
     artificially
    0.07
    เฟ
    0.06
    _starts
    0.06
     Cont
    0.06
     Prescription
    0.06
    Cont
    0.06
    Act Density 0.001%

    No Known Activations