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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMP
    -0.07
     svět
    -0.07
    ภาพ
    -0.07
    .Tween
    -0.06
     kış
    -0.06
    iae
    -0.06
    ورش
    -0.06
    Dep
    -0.06
    やる
    -0.06
    fp
    -0.06
    POSITIVE LOGITS
    обав
    0.06
    OfBirth
    0.06
    .attack
    0.06
     letras
    0.06
    .copyOf
    0.06
     recebe
    0.06
    ufact
    0.06
     civ
    0.06
    .--
    0.06
     regimes
    0.06
    Act Density 0.122%

    No Known Activations