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

    Neuronpedia

    INDEX
    Explanations

    the letter "E" in the context of solving a math or logic puzzle

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    li
    -0.12
    ss
    -0.12
    ness
    -0.11
    so
    -0.11
    m
    -0.11
    x
    -0.11
    ne
    -0.11
    lo
    -0.10
    ver
    -0.10
    nya
    -0.10
    POSITIVE LOGITS
    hx
    0.08
    .g
    0.08
     plur
    0.08
    uforia
    0.08
    iad
    0.07
    iac
    0.07
    iare
    0.07
    iras
    0.07
    onet
    0.07
    etak
    0.07
    Act Density 0.163%

    No Known Activations