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

    Neuronpedia

    INDEX
    Explanations

    scientific paper introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    å¼Ľ
    -0.31
    è¶ĭ
    -0.26
    ursed
    -0.26
    iled
    -0.25
     melted
    -0.25
    UCH
    -0.25
     minded
    -0.25
    æ©Ľ
    -0.24
    aned
    -0.24
    __('
    -0.24
    POSITIVE LOGITS
    ble
    0.28
    ç¡İ
    0.27
     conflicting
    0.27
    足
    0.26
    æ´µ
    0.26
     thought
    0.25
     correspond
    0.25
     mÃŃ
    0.25
    la
    0.25
    åĽĽå¤Ħ
    0.24
    Act Density 0.005%

    No Known Activations