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

    Neuronpedia

    INDEX
    Explanations

    C++ iostream and file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    porque
    0.73
    cuando
    0.72
    Quando
    0.68
    Org
    0.67
    Avec
    0.66
    intensive
    0.66
    Aryan
    0.66
    Apple
    0.65
    Ginger
    0.64
    Oracle
    0.64
    POSITIVE LOGITS
     collections
    0.72
     glTexParameteri
    0.60
     nailed
    0.59
     contentLength
    0.57
     fairness
    0.55
     negotiations
    0.55
    Tokenizer
    0.55
     released
    0.54
    Charsets
    0.53
     cracking
    0.53
    Act Density 0.025%

    No Known Activations