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

    Neuronpedia

    INDEX
    Explanations

    Declaration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشک
    -0.07
    anticipated
    -0.06
     toi
    -0.06
     téléphone
    -0.06
     καν
    -0.06
     potvr
    -0.06
     vistas
    -0.06
    carbon
    -0.06
    万円
    -0.06
     weighs
    -0.06
    POSITIVE LOGITS
     Buddhist
    0.07
    allel
    0.07
    _vector
    0.07
     charismatic
    0.07
    nych
    0.07
     passive
    0.06
    Creat
    0.06
    _report
    0.06
     renaming
    0.06
     Assign
    0.06
    Act Density 0.012%

    No Known Activations