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

    Neuronpedia

    INDEX
    Explanations

    Unsafe water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tw
    -0.06
     advisors
    -0.06
     dcc
    -0.06
    ramid
    -0.06
    ी,
    -0.06
     Control
    -0.06
    .Blue
    -0.06
     errorThrown
    -0.06
     Compar
    -0.06
    _SHIFT
    -0.06
    POSITIVE LOGITS
    /users
    0.07
    (mark
    0.06
     nhóm
    0.06
    nie
    0.06
     PRES
    0.06
    _po
    0.06
     Sb
    0.06
     kì
    0.06
    召
    0.06
    _rs
    0.06
    Act Density 0.039%

    No Known Activations