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

    Neuronpedia

    INDEX
    Explanations

    fingers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Touchable
    -0.08
    住宅
    -0.08
     stretchy
    -0.08
     površ
    -0.07
    旅游
    -0.07
    自治
    -0.07
     erroneous
    -0.07
    yuan
    -0.07
     erforder
    -0.07
    jährige
    -0.07
    POSITIVE LOGITS
    mom
    0.09
     bambini
    0.09
     Orchestra
    0.09
     écl
    0.08
     Sequence
    0.08
     పిల్ల
    0.08
     louder
    0.08
     sequence
    0.08
     гром
    0.08
     orchestra
    0.08
    Act Density 0.001%

    No Known Activations