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

    Neuronpedia

    INDEX
    Explanations

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     संचालन
    0.77
     因
    0.75
     Fa
    0.74
     vše
    0.73
     consultato
    0.72
     charge
    0.71
    uli
    0.71
    ئے
    0.70
     മുഴുവ
    0.70
    каза
    0.70
    POSITIVE LOGITS
    about
    0.62
     محر
    0.58
     essentially
    0.57
    highlight
    0.55
    apol
    0.55
    γων
    0.53
     //
    0.53
     fundamentally
    0.52
     муж
    0.52
    automatically
    0.52
    Act Density 0.068%

    No Known Activations