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

    Neuronpedia

    INDEX
    Explanations

    allo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    捭
    -0.07
    margin
    -0.07
    ashion
    -0.07
    以前
    -0.07
     Timestamp
    -0.07
    דר
    -0.07
     real
    -0.07
    gu
    -0.07
    Um
    -0.07
    fn
    -0.07
    POSITIVE LOGITS
     wf
    0.08
    城管
    0.07
    Recorder
    0.07
    脎
    0.07
    /tcp
    0.07
     cioè
    0.07
    دراج
    0.06
    不动
    0.06
     Locker
    0.06
     mailbox
    0.06
    Act Density 0.002%

    No Known Activations