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

    Neuronpedia

    INDEX
    Explanations

    -pane

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slot
    -0.06
    civil
    -0.06
     stair
    -0.06
     dwell
    -0.06
     prefs
    -0.06
     redesign
    -0.06
    	buffer
    -0.06
    yun
    -0.06
     hesitate
    -0.06
     PM
    -0.06
    POSITIVE LOGITS
     Requirements
    0.07
    roscope
    0.06
     arranged
    0.06
     на
    0.06
    哦
    0.06
     sonu
    0.06
    keep
    0.06
     Bryant
    0.06
    ivní
    0.06
    	↵	↵↵
    0.06
    Act Density 0.008%

    No Known Activations