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

    Neuronpedia

    INDEX
    Explanations

    John followed by a surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resa
    -0.92
    eater
    -0.82
     Gleaner
    -0.81
     transporta
    -0.80
     circula
    -0.80
    degradation
    -0.80
    komen
    -0.77
    clientY
    -0.77
     perhaps
    -0.75
     Premio
    -0.75
    POSITIVE LOGITS
     strait
    0.86
     Abstand
    0.84
     auft
    0.77
     Idea
    0.76
    restart
    0.74
     outsole
    0.72
     Tey
    0.71
    やってきた
    0.71
     JF
    0.71
     xiii
    0.71
    Act Density 0.064%

    No Known Activations