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

    Neuronpedia

    INDEX
    Explanations

    Portuguese language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fatal
    -0.07
     FIXME
    -0.07
     proud
    -0.06
    _questions
    -0.06
    	password
    -0.06
    ksam
    -0.06
    ертв
    -0.06
     [('
    -0.06
     Projekt
    -0.06
    modify
    -0.06
    POSITIVE LOGITS
     very
    0.06
     Arr
    0.06
    essoa
    0.06
     jumps
    0.06
     fragmentation
    0.06
    Organ
    0.06
     CERT
    0.06
     vrch
    0.05
    647
    0.05
    Votre
    0.05
    Act Density 0.079%

    No Known Activations