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

    Neuronpedia

    INDEX
    Explanations

    Bach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spir
    -0.26
     Amir
    -0.25
     shocks
    -0.25
    instant
    -0.25
     needles
    -0.25
    è«ĩ
    -0.25
    hours
    -0.24
    åĩłåĪĨéĴŁ
    -0.24
     hours
    -0.24
    éĵº
    -0.23
    POSITIVE LOGITS
    uden
    0.27
    åĩĮ
    0.26
    oko
    0.26
    客
    0.26
    ude
    0.25
    åIJĮå¿Ĺ
    0.25
    ä½Ĩ她
    0.25
    åĽłä¸ºå¥¹
    0.24
    guest
    0.24
     év
    0.24
    Act Density 0.561%

    No Known Activations