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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sack
    -0.06
     σου
    -0.06
     strives
    -0.06
    	The
    -0.06
     caravan
    -0.06
     Austrian
    -0.06
    bra
    -0.06
     Chile
    -0.06
     στι
    -0.06
    epy
    -0.06
    POSITIVE LOGITS
     Peoples
    0.07
    unsqueeze
    0.06
    _pago
    0.06
    iators
    0.06
    ontvangst
    0.06
    _shader
    0.06
    _EDEFAULT
    0.06
    _backward
    0.06
     ZX
    0.06
    _ground
    0.06
    Act Density 0.052%

    No Known Activations