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

    Neuronpedia

    INDEX
    Explanations

    fre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aw
    -0.09
    ain
    -0.08
     Hasan
    -0.08
    ault
    -0.08
     Jain
    -0.07
    oid
    -0.07
    ahn
    -0.07
     Said
    -0.07
    オン
    -0.07
    az
    -0.07
    POSITIVE LOGITS
     Gre
    0.12
     Fre
    0.11
    Gre
    0.11
     Gro
    0.11
    Fre
    0.10
     tre
    0.10
     Tre
    0.09
     Flo
    0.09
     Bre
    0.09
     Fro
    0.09
    Act Density 0.079%

    No Known Activations