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

    Neuronpedia

    INDEX
    Explanations

    asking questions about you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Invoke
    0.56
     obsessive
    0.55
     obsess
    0.55
     dogged
    0.55
     Damn
    0.54
     hostilities
    0.53
     sadistic
    0.52
     extortion
    0.51
     its
    0.50
     parody
    0.50
    POSITIVE LOGITS
    みんな
    0.65
     especiales
    0.64
     mommy
    0.63
     पापा
    0.61
    たくさん
    0.61
     ayudan
    0.61
     hermoso
    0.61
     tummy
    0.59
     manchmal
    0.59
    媽媽
    0.59
    Act Density 0.509%

    No Known Activations