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

    Neuronpedia

    INDEX
    Explanations

    34

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sup
    -0.07
     Assistance
    -0.07
     imminent
    -0.06
     Various
    -0.06
    že
    -0.06
     bother
    -0.06
    業務
    -0.06
    Sur
    -0.06
    _call
    -0.06
    �장
    -0.06
    POSITIVE LOGITS
    0.07
    0.07
    -analytics
    0.07
     reflexivity
    0.06
     |-
    0.06
     tỏ
    0.06
    तम
    0.06
    	        ↵
    0.06
    éra
    0.06
    (reinterpret
    0.06
    Act Density 0.000%

    No Known Activations