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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ys
    -0.27
    å½ĵåĪĿ
    -0.26
    Signing
    -0.26
    ç°½
    -0.24
    ç¢į
    -0.24
    è¿Ľä¸ĢæŃ¥
    -0.24
     Aval
    -0.24
     sooner
    -0.23
    ç½
    -0.23
     Cities
    -0.23
    POSITIVE LOGITS
    æĽĿåħī
    0.29
    ties
    0.26
    .Center
    0.25
    ubar
    0.25
    elts
    0.25
    wards
    0.24
    髦
    0.23
    swith
    0.23
     scrutiny
    0.23
    HOOK
    0.23
    Act Density 0.206%

    No Known Activations