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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    験
    -0.08
    повід
    -0.07
     McKay
    -0.07
    -approved
    -0.07
    bias
    -0.07
     stout
    -0.07
    ีเด
    -0.07
     CreateUser
    -0.06
    つの
    -0.06
     Savior
    -0.06
    POSITIVE LOGITS
    Swagger
    0.07
    /v
    0.06
     MB
    0.06
     SEARCH
    0.06
     Limit
    0.06
    Hook
    0.06
     collected
    0.06
     abilities
    0.05
     horrible
    0.05
    >tag
    0.05
    Act Density 0.008%

    No Known Activations