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

    Neuronpedia

    INDEX
    Explanations

    lication endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,password
    -0.07
    ΟΔ
    -0.07
     lou
    -0.06
     Manage
    -0.06
     CTRL
    -0.06
    XS
    -0.06
     gou
    -0.06
     goalt
    -0.06
    airy
    -0.06
    Beam
    -0.06
    POSITIVE LOGITS
     llev
    0.07
     PPP
    0.07
     implic
    0.07
     implementing
    0.07
    หาก
    0.07
     implicated
    0.06
    برد
    0.06
     implications
    0.06
     userData
    0.06
    นำ
    0.06
    Act Density 0.008%

    No Known Activations