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

    Neuronpedia

    INDEX
    Explanations

    seaside locations and seaweed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.03
     transnational
    0.89
     combatt
    0.87
     supremely
    0.84
     günst
    0.84
     perilous
    0.82
     have
    0.81
    子
    0.81
     relacion
    0.80
    ()=>{
    0.80
    POSITIVE LOGITS
    ان
    1.19
    ac
    1.16
    ut
    0.93
    ater
    0.90
    ars
    0.89
    ан
    0.84
    t
    0.84
    ri
    0.83
    inha
    0.81
    ade
    0.80
    Act Density 0.001%

    No Known Activations