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

    Neuronpedia

    INDEX
    Explanations

    contrasting or clarifying boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сахар
    0.42
    stations
    0.40
     restricciones
    0.40
     نړ
    0.40
     संयंत्र
    0.39
    START
    0.38
    Stations
    0.38
    禦
    0.37
    流量
    0.37
    triggers
    0.37
    POSITIVE LOGITS
     parallel
    0.41
     Parallel
    0.39
     paralel
    0.39
     penultimate
    0.39
     contemplated
    0.37
     perplexed
    0.37
    Parallel
    0.37
    ยาว
    0.37
     กู
    0.36
    SetFloat
    0.36
    Act Density 0.017%

    No Known Activations