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

    Neuronpedia

    INDEX
    Explanations

    descriptions of hardness and durability in materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    description of firmness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.44
     voglia
    -0.38
     أخ
    -0.36
    lamp
    -0.35
    hop
    -0.33
    രിക്ക
    -0.31
    SequentialGroup
    -0.30
    demo
    -0.30
    doc
    -0.29
     hope
    -0.29
    POSITIVE LOGITS
     hardness
    0.75
     Hard
    0.69
     initComponents
    0.69
    Hardness
    0.69
    硬
    0.69
    Hard
    0.68
     harde
    0.67
     hard
    0.67
     cứng
    0.66
     harden
    0.66
    Act Density 0.015%

    No Known Activations