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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    civil
    -0.07
     Eine
    -0.07
    声
    -0.07
    ΗΝ
    -0.06
    드립니다
    -0.06
     دخ
    -0.06
     catalogue
    -0.06
    _PIN
    -0.06
    atalog
    -0.06
    	echo
    -0.06
    POSITIVE LOGITS
    (feature
    0.07
     maxim
    0.07
    culator
    0.07
     حتی
    0.06
    у
    0.06
     IAM
    0.06
     menstrual
    0.06
    -push
    0.06
     minValue
    0.06
     możli
    0.06
    Act Density 0.023%

    No Known Activations