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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IMO
    -0.07
     lawmakers
    -0.07
    𦙶
    -0.07
    哪里
    -0.07
     morals
    -0.07
    扩建
    -0.07
    _PAUSE
    -0.07
    מוסר
    -0.07
     Harbor
    -0.07
     motives
    -0.07
    POSITIVE LOGITS
     jav
    0.08
    _mesh
    0.07
    _printf
    0.07
     cpp
    0.07
     beğ
    0.07
    cff
    0.07
     ka
    0.07
     arrang
    0.07
    sns
    0.07
    %%
    0.06
    Act Density 0.006%

    No Known Activations