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

    Neuronpedia

    INDEX
    Explanations

    proposing interactive activities or discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ícios
    0.46
     یقینی
    0.42
     sacrifices
    0.40
    knowing
    0.40
    Ensure
    0.39
     sacrificio
    0.39
     interception
    0.39
    帑
    0.39
    മുഖ
    0.38
     assicur
    0.38
    POSITIVE LOGITS
     brainstorm
    1.34
     brainstorming
    1.06
     collaboratively
    0.93
     discuss
    0.91
     explore
    0.89
     Discuss
    0.85
     Brain
    0.85
    Brain
    0.81
     discussing
    0.79
    discuss
    0.77
    Act Density 0.097%

    No Known Activations