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

    Neuronpedia

    INDEX
    Explanations

    idea that, ability to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.60
    }$
    0.49
     a
    0.48
    0.46
    },
    0.45
    }
    0.45
    場合
    0.42
     its
    0.41
     your
    0.41
     this
    0.41
    POSITIVE LOGITS
    uradaki
    0.54
    arın
    0.53
    िक्
    0.51
    ēng
    0.50
     ఆఫ్
    0.45
    panelMenuList
    0.45
    ığın
    0.45
     centrality
    0.45
    ociation
    0.44
     saada
    0.44
    Act Density 0.025%

    No Known Activations