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

    Neuronpedia

    INDEX
    Explanations

    Hartree-Fock theory

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cycle
    -0.07
     Weber
    -0.06
    elo
    -0.06
     ken
    -0.06
    Furthermore
    -0.06
     recurse
    -0.06
    Produ
    -0.06
     fout
    -0.06
    кая
    -0.06
     Valid
    -0.06
    POSITIVE LOGITS
     lượng
    0.07
    θι
    0.07
     =========================================================================
    0.06
     CHE
    0.06
     뛰
    0.06
    twenty
    0.06
     него
    0.06
    ้าห
    0.06
     points
    0.06
     strengthen
    0.06
    Act Density 0.011%

    No Known Activations