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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OfType
    -0.08
    _GP
    -0.07
     nám
    -0.07
     dní
    -0.06
    _rq
    -0.06
                
    -0.06
    �
    -0.06
     Theater
    -0.06
     UnityEngine
    -0.06
     zeigt
    -0.06
    POSITIVE LOGITS
    <Real
    0.07
    Genesis
    0.07
    Gal
    0.07
     ApplicationUser
    0.06
     BLUE
    0.06
    base
    0.06
    -prom
    0.06
    早
    0.06
    .String
    0.06
    opal
    0.06
    Act Density 0.000%

    No Known Activations