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

    Neuronpedia

    INDEX
    Explanations

    mysterious disappearances and investigations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تصور
    0.50
     estrategias
    0.49
     страте
    0.49
     strategie
    0.48
    strategies
    0.46
     besta
    0.44
     انواع
    0.44
     strategies
    0.44
     Strategies
    0.42
     evolve
    0.42
    POSITIVE LOGITS
     disappearance
    0.69
     mysterious
    0.67
     murders
    0.65
     disappear
    0.64
     mysteriously
    0.64
     deaths
    0.63
     killings
    0.63
    神秘
    0.62
     experimentos
    0.61
     murdered
    0.59
    Act Density 0.028%

    No Known Activations