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

    Neuronpedia

    INDEX
    Explanations

    solving algebraic equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createWindow
    0.37
    щь
    0.37
    Melitaea
    0.37
     millis
    0.36
     jedin
    0.35
    initState
    0.35
    Isolated
    0.35
     lateribus
    0.35
    嘧
    0.35
     instructing
    0.35
    POSITIVE LOGITS
    nop
    0.54
    move
    0.53
     subtract
    0.52
    add
    0.52
    subtract
    0.49
    iget
    0.49
     Subtract
    0.49
     nop
    0.48
    assumption
    0.46
    aget
    0.46
    Act Density 0.002%

    No Known Activations