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

    Neuronpedia

    INDEX
    Explanations

    general english conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fich
    -0.07
     лист
    -0.07
     mild
    -0.06
     conspicuous
    -0.06
     circumcision
    -0.06
    Waiting
    -0.06
    	list
    -0.06
    regation
    -0.06
    Ctl
    -0.06
    :event
    -0.06
    POSITIVE LOGITS
    (ctx
    0.07
     αν
    0.07
    amu
    0.07
    ocht
    0.07
    _DEAD
    0.06
     obscene
    0.06
    �
    0.06
    ellido
    0.06
     bucks
    0.06
    lyph
    0.06
    Act Density 0.412%

    No Known Activations