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

    Neuronpedia

    INDEX
    Explanations

    nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     They
    -0.07
     potentials
    -0.07
    linear
    -0.07
    atical
    -0.07
    「あ
    -0.07
     they
    -0.07
     kinase
    -0.07
    .multipart
    -0.07
     There
    -0.07
    urai
    -0.06
    POSITIVE LOGITS
    _tcb
    0.06
     Monument
    0.06
    pom
    0.06
     —
    0.06
    ）的
    0.06
     interesse
    0.06
    Dept
    0.06
    stanov
    0.06
    MU
    0.06
     soudu
    0.06
    Act Density 0.207%

    No Known Activations