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

    Neuronpedia

    INDEX
    Explanations

    ease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    现有的
    -0.07
    لف
    -0.06
    ожно
    -0.06
    /new
    -0.06
    ient
    -0.06
    和完善
    -0.06
    Administrator
    -0.06
    Ph
    -0.06
    лект
    -0.06
     tuyển
    -0.06
    POSITIVE LOGITS
     despre
    0.07
    悸
    0.07
    	debug
    0.07
    砮
    0.07
     compens
    0.07
     prefixes
    0.07
     ga
    0.06
     inverse
    0.06
    彳
    0.06
    سبب
    0.06
    Act Density 0.005%

    No Known Activations