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

    Neuronpedia

    INDEX
    Explanations

    positive numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gru
    -0.09
     esf
    -0.08
     한번
    -0.08
    uga
    -0.08
     групп
    -0.08
     Einheit
    -0.07
    indow
    -0.07
     gioco
    -0.07
     beschad
    -0.07
     одна
    -0.07
    POSITIVE LOGITS
    -positive
    0.12
     positive
    0.12
    positive
    0.11
     positives
    0.11
     positif
    0.11
     positivity
    0.10
     सकारात्मक
    0.09
     Positive
    0.09
     positiva
    0.09
     positivos
    0.09
    Act Density 0.126%

    No Known Activations