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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helicopter
    -0.06
     水
    -0.06
    となる
    -0.06
    찰
    -0.06
    _restore
    -0.06
    .dev
    -0.06
     sefer
    -0.06
     tension
    -0.06
     금
    -0.06
    Vectors
    -0.06
    POSITIVE LOGITS
    /in
    0.08
    lijke
    0.07
     JUST
    0.07
    Campo
    0.07
     슬
    0.07
    」の
    0.06
    RIEND
    0.06
     pagar
    0.06
    Nuevo
    0.06
    .y
    0.06
    Act Density 0.005%

    No Known Activations