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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĭĶ
    -0.27
    ummer
    -0.27
    éĥ¨éŨ
    -0.26
     Visualization
    -0.26
    çļĦæĹ¥åŃIJéĩĮ
    -0.25
    Protected
    -0.25
    unate
    -0.25
     blat
    -0.24
    åĪĨå±Ģ
    -0.24
    cow
    -0.24
    POSITIVE LOGITS
    è°Ī论
    0.28
    idi
    0.27
     referring
    0.27
    车çīĮ
    0.27
     uf
    0.26
     chemistry
    0.26
     deutsch
    0.26
    ä»ĭç»į
    0.26
    chemistry
    0.25
    ç®ĢåİĨ
    0.25
    Act Density 0.006%

    No Known Activations