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

    Neuronpedia

    INDEX
    Explanations

    how mutations occur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Shang
    0.47
    berg
    0.45
    Nx
    0.43
    createdAt
    0.42
    ile
    0.42
    логі
    0.41
    нді
    0.41
    季
    0.40
    发现
    0.40
    ori
    0.40
    POSITIVE LOGITS
     pessoais
    0.54
     chacun
    0.51
     personales
    0.49
     hänen
    0.48
     Neend
    0.48
     seinem
    0.47
     individuals
    0.47
     sardines
    0.47
     tomando
    0.46
     recue
    0.46
    Act Density 0.018%

    No Known Activations