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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    อบรม
    -0.08
    DTD
    -0.08
    .GET
    -0.07
    ✗
    -0.07
    陌生
    -0.07
    莳
    -0.07
    鸠
    -0.07
     vaguely
    -0.07
     gradual
    -0.07
     géné
    -0.07
    POSITIVE LOGITS
    	l
    0.08
    Yeah
    0.07
    	payload
    0.07
    ṇ
    0.07
     Agricultural
    0.07
    Invariant
    0.06
     ficken
    0.06
    stdlib
    0.06
    0.06
     switching
    0.06
    Act Density 0.000%

    No Known Activations