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

    Neuronpedia

    INDEX
    Explanations

    explaining the meaning of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     austerity
    0.43
     poly
    0.43
     graphene
    0.43
     palate
    0.43
     transgression
    0.43
     pursuit
    0.42
     silicon
    0.42
     mus
    0.41
     altitude
    0.41
     delicacies
    0.41
    POSITIVE LOGITS
     Formatting
    0.54
    arki
    0.53
    窜
    0.44
     formularios
    0.44
    formatting
    0.43
     Customizable
    0.43
    ativo
    0.43
    enfants
    0.42
    geräte
    0.42
     Laravel
    0.42
    Act Density 0.006%

    No Known Activations