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

    Neuronpedia

    INDEX
    Explanations

    pointer dereference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    1.01
    ه
    0.96
    er
    0.91
    ter
    0.82
    ం
    0.80
    ी
    0.76
    ת
    0.76
    lo
    0.73
    iatric
    0.71
    icts
    0.70
    POSITIVE LOGITS
    ற்போது
    0.76
     notch
    0.73
     weiteres
    0.70
     lookup
    0.68
    𝐬
    0.66
     beras
    0.65
     mitad
    0.65
    propelled
    0.65
     bump
    0.65
    ನಲ್ಲಿ
    0.64
    Act Density 0.883%

    No Known Activations