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

    Neuronpedia

    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     develop
    -0.06
     поб
    -0.06
    stacles
    -0.06
     dislike
    -0.06
    btn
    -0.06
     그래서
    -0.06
     inefficient
    -0.06
     affine
    -0.06
    KD
    -0.06
    getObject
    -0.06
    POSITIVE LOGITS
     mattered
    0.12
     matters
    0.10
     Matters
    0.08
    له
    0.07
    ijkl
    0.07
    abcd
    0.07
     count
    0.07
     cél
    0.07
     celebrity
    0.07
    Only
    0.07
    Act Density 0.009%

    No Known Activations