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

    Neuronpedia

    INDEX
    Explanations

    checklist items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revelation
    -0.08
    -0.08
     دلیل
    -0.07
     لتع
    -0.07
     samot
    -0.07
     differently
    -0.07
    利来
    -0.07
    扱
    -0.07
    udis
    -0.07
     ideals
    -0.07
    POSITIVE LOGITS
     Correct
    0.11
     mindestens
    0.11
     almeno
    0.11
    Correct
    0.11
    _correct
    0.11
     minstens
    0.10
     своев
    0.10
     correctamente
    0.10
     सही
    0.10
     לפחות
    0.10
    Act Density 0.012%
    No Known Activations