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

    Neuronpedia

    INDEX
    Explanations

    roles and machine learning assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ［
    0.47
    ◾
    0.40
     integrable
    0.39
     －
    0.39
    0.38
     짜
    0.38
    ij
    0.38
    :[/
    0.38
    0.38
    ▌
    0.38
    POSITIVE LOGITS
     racking
    0.45
     racked
    0.43
    емый
    0.41
     mapper
    0.39
     HashMap
    0.39
     toto
    0.38
     Sage
    0.38
     pip
    0.38
     alloc
    0.38
     singled
    0.38
    Act Density 0.005%

    No Known Activations