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

    Neuronpedia

    INDEX
    Explanations

    explaining evaluation methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pasting
    0.46
    Morgan
    0.42
     Initiative
    0.42
    Selecting
    0.40
    Ivoire
    0.39
     Atlantic
    0.38
     Marquette
    0.38
     প্রভু
    0.38
     Observation
    0.37
     embossing
    0.37
    POSITIVE LOGITS
    stall
    0.38
    야
    0.37
     кру
    0.36
    ridine
    0.36
    getBlueTeam
    0.36
     profissional
    0.36
    communities
    0.36
     historias
    0.34
     рад
    0.34
    ધન
    0.34
    Act Density 0.001%

    No Known Activations