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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	move
    -0.07
    春风
    -0.07
     sign
    -0.07
     Latina
    -0.07
     Connecting
    -0.06
     Revenge
    -0.06
    .portal
    -0.06
     stronger
    -0.06
    艺
    -0.06
     Forum
    -0.06
    POSITIVE LOGITS
    city
    0.07
    assandra
    0.07
    לנד
    0.07
    צור
    0.07
    קיב
    0.07
    מט
    0.07
    _LO
    0.07
     humid
    0.07
     clandest
    0.07
    agnost
    0.06
    Act Density 0.002%

    No Known Activations