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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .edges
    -0.07
     DBNull
    -0.06
    Bullet
    -0.06
    asyarakat
    -0.06
     Potter
    -0.06
    kap
    -0.06
     rationale
    -0.06
    ivel
    -0.06
     dicks
    -0.06
     potrze
    -0.06
    POSITIVE LOGITS
    شه
    0.07
    Kind
    0.07
    (sign
    0.07
    姓名
    0.06
    ;break
    0.06
     तक
    0.06
     merg
    0.06
     END
    0.06
     желуд
    0.06
    г
    0.06
    Act Density 0.026%

    No Known Activations