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

    Neuronpedia

    INDEX
    Explanations

    how things are framed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Maple
    0.47
    BUFF
    0.41
    SIBILITY
    0.38
    Todd
    0.38
    0.38
    DAN
    0.37
    Excerpt
    0.37
    リン
    0.37
    uscany
    0.37
    アジア
    0.36
    POSITIVE LOGITS
     Personnel
    0.41
    ரிடம்
    0.40
     personnel
    0.39
     lar
    0.38
     Personal
    0.38
     Display
    0.38
     Games
    0.37
     fro
    0.37
     insertions
    0.37
     expresa
    0.36
    Act Density 0.001%

    No Known Activations