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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     под
    -0.07
     volumes
    -0.07
     edition
    -0.07
    -phase
    -0.07
     있도록
    -0.07
    /lo
    -0.07
    encias
    -0.07
    suspend
    -0.07
     iphone
    -0.06
     fragments
    -0.06
    POSITIVE LOGITS
     trở
    0.07
     ruk
    0.06
     Walk
    0.06
    SIGN
    0.06
    ِك
    0.06
     /^[
    0.06
     rapper
    0.06
     домаш
    0.06
     happily
    0.06
    mailer
    0.06
    Act Density 0.013%

    No Known Activations