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

    Neuronpedia

    INDEX
    Explanations

    "=@"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     irony
    -0.07
     Singer
    -0.06
     Carmen
    -0.06
     steel
    -0.06
    /base
    -0.06
     steal
    -0.06
    ldr
    -0.06
     mole
    -0.06
    میل
    -0.06
     glo
    -0.06
    POSITIVE LOGITS
     strains
    0.07
     Attempts
    0.07
     благ
    0.07
    대학교
    0.07
     シ
    0.06
    >');↵
    0.06
     elemental
    0.06
     asm
    0.06
    hasMany
    0.06
     外部リンク
    0.06
    Act Density 0.001%

    No Known Activations