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

    Neuronpedia

    INDEX
    Explanations

    boost library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cade
    -0.08
     ста
    -0.07
    …but
    -0.07
     leans
    -0.07
    Meg
    -0.07
    phrase
    -0.07
    ebin
    -0.06
    Cost
    -0.06
     Pierce
    -0.06
     đem
    -0.06
    POSITIVE LOGITS
     krb
    0.06
    LECT
    0.06
    texture
    0.06
    embros
    0.06
     니
    0.06
     Dental
    0.06
    reflect
    0.05
     ΚΑΙ
    0.05
                                    
    0.05
     Radeon
    0.05
    Act Density 0.002%

    No Known Activations