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

    Neuronpedia

    INDEX
    Explanations

    hr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _POINT
    -0.08
     fibre
    -0.07
    ].'
    -0.06
     Optimization
    -0.06
     ска
    -0.06
     ее
    -0.06
    ish
    -0.06
    _to
    -0.06
     DOI
    -0.06
    ),
    -0.06
    POSITIVE LOGITS
    <hr
    0.15
    hr
    0.13
    HR
    0.10
    (hr
    0.10
    	hr
    0.10
     HRESULT
    0.09
     hr
    0.08
    thr
    0.08
    .slf
    0.07
    .hr
    0.07
    Act Density 0.002%

    No Known Activations