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

    Neuronpedia

    INDEX
    Explanations

    written works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auer
    -0.07
     Against
    -0.07
    ponents
    -0.06
    яют
    -0.06
     salaries
    -0.06
     OVER
    -0.06
    oked
    -0.06
     detection
    -0.06
     instructions
    -0.06
    ARED
    -0.06
    POSITIVE LOGITS
    MeshPro
    0.07
    OneToMany
    0.06
     PublicKey
    0.06
    �试
    0.06
     />,
    0.06
    ,pos
    0.06
     मल
    0.06
     �
    0.06
    umblr
    0.06
    جن
    0.06
    Act Density 0.022%

    No Known Activations