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

    Neuronpedia

    INDEX
    Explanations

    tutoring and education

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melted
    -0.07
     Warranty
    -0.07
     Infinity
    -0.07
     unmanned
    -0.07
    万科
    -0.06
    YE
    -0.06
     npc
    -0.06
     универ
    -0.06
    neider
    -0.06
    ᴓ
    -0.06
    POSITIVE LOGITS
     registers
    0.07
    przedsiębior
    0.07
    比
    0.07
     Wish
    0.07
    competition
    0.07
    Happy
    0.07
    _bits
    0.07
    参加
    0.07
    сим
    0.07
     Representation
    0.07
    Act Density 0.008%

    No Known Activations