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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    順
    -0.07
     takes
    -0.07
    VarInsn
    -0.06
     Like
    -0.06
    ፡
    -0.06
     merupakan
    -0.06
    ALTH
    -0.06
    upakan
    -0.06
    рма
    -0.06
     Police
    -0.06
    POSITIVE LOGITS
    /Table
    0.08
     breeds
    0.07
     inconvenient
    0.07
    essor
    0.07
     Draco
    0.07
     geil
    0.07
     Adding
    0.07
    /Observable
    0.07
    _deck
    0.06
    _listing
    0.06
    Act Density 0.000%

    No Known Activations