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

    Neuronpedia

    INDEX
    Explanations

    Rhetorical questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーの
    -0.07
    _Sh
    -0.07
     Parameters
    -0.07
     Stranger
    -0.06
     scene
    -0.06
    .af
    -0.06
     робити
    -0.06
     complex
    -0.06
    Fixed
    -0.06
    칠
    -0.06
    POSITIVE LOGITS
     Ritch
    0.06
    reen
    0.06
    altung
    0.06
    ).^
    0.06
    reo
    0.06
    enschaft
    0.06
    пня
    0.06
    irit
    0.06
    adık
    0.06
    jm
    0.06
    Act Density 0.073%

    No Known Activations