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

    Neuronpedia

    INDEX
    Explanations

    LGBTQ youth support services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.92
     can
    0.80
     will
    0.72
     in
    0.71
    3
    0.70
     are
    0.59
    U
    0.59
    ש
    0.58
    िया
    0.56
    d
    0.56
    POSITIVE LOGITS
     deras
    0.64
     invitados
    0.60
    Ꮸ
    0.55
    )。
    0.54
    ны
    0.54
     behaupt
    0.53
     práct
    0.51
    ový
    0.50
    Ngoài
    0.50
     putern
    0.50
    Act Density 0.276%

    No Known Activations