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

    Neuronpedia

    INDEX
    Explanations

    verbs related to evading or resisting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    no followed by certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    السكان
    -0.44
     instituciones
    -0.41
     basura
    -0.38
     distribuição
    -0.35
     senhora
    -0.35
     Anfitrión
    -0.35
     distribución
    -0.34
     silvestre
    -0.33
     vidro
    -0.33
     necessidades
    -0.33
    POSITIVE LOGITS
    $_(
    0.59
     Roskov
    0.56
    DataAnnotations
    0.54
    0.52
    /**
    0.51
    kug
    0.50
    }$​
    0.49
    ſammen
    0.49
    timate
    0.49
    AccessorTable
    0.48
    Act Density 0.031%

    No Known Activations