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

    Neuronpedia

    INDEX
    Explanations

    .com, Blob Storage, villages for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rm
    0.49
    getRedTeam
    0.44
    Sprintf
    0.43
    keits
    0.43
    ther
    0.43
    ties
    0.43
    vel
    0.42
    рд
    0.42
    riko
    0.41
    rim
    0.41
    POSITIVE LOGITS
     thứ
    0.57
     cancé
    0.52
     tratta
    0.48
     Yah
    0.47
    ců
    0.46
     aisl
    0.46
     Noh
    0.45
     strana
    0.45
     CRO
    0.45
     назнача
    0.45
    Act Density 0.000%

    No Known Activations