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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disbursement
    0.52
    fledged
    0.51
     کرنے
    0.49
    ের
    0.49
     DevOps
    0.48
     neuroscience
    0.47
    نہ
    0.47
     SDGs
    0.46
     Dalit
    0.46
     initializes
    0.46
    POSITIVE LOGITS
    은
    0.58
    К
    0.55
    Я
    0.54
    ^
    0.52
    ੜ
    0.51
    ۱
    0.50
    `
    0.49
    েইলি
    0.49
    ay
    0.47
    and
    0.46
    Act Density 0.000%

    No Known Activations