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

    Neuronpedia

    INDEX
    Explanations

    error message specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ALLOC
    0.43
    alloc
    0.42
    Alloc
    0.42
    data
    0.39
     monet
    0.38
     Immunol
    0.38
    Allocation
    0.38
     allocate
    0.37
     greed
    0.37
     alloc
    0.37
    POSITIVE LOGITS
     underm
    0.43
    👂
    0.39
     Ideas
    0.37
     अगले
    0.37
     Tada
    0.36
     IDEA
    0.36
    糺
    0.36
    ="...">
    0.35
    ativen
    0.35
    >=</
    0.35
    Act Density 0.000%

    No Known Activations