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

    Neuronpedia

    INDEX
    Explanations

    IP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     �
    -0.07
     Freund
    -0.07
    �
    -0.07
     Tamb
    -0.07
     Carlson
    -0.07
     bundan
    -0.07
     Wednesday
    -0.07
     Carn
    -0.07
     dancer
    -0.07
    POSITIVE LOGITS
     IP
    0.14
    IP
    0.13
    ip
    0.12
     Ip
    0.12
    _ip
    0.11
     ip
    0.11
    Ip
    0.10
     I
    0.09
    (ip
    0.09
     IPv
    0.09
    Act Density 0.010%

    No Known Activations