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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     То
    -0.07
     قرارد
    -0.07
     hombre
    -0.06
    ierre
    -0.06
    願い
    -0.06
    Cluster
    -0.06
    ldr
    -0.06
     downright
    -0.06
    gem
    -0.06
     Harvey
    -0.06
    POSITIVE LOGITS
    Indent
    0.07
    -dis
    0.07
     течение
    0.07
     během
    0.07
     suit
    0.07
    -ab
    0.07
    :Boolean
    0.06
     &,
    0.06
     dealloc
    0.06
    �
    0.06
    Act Density 0.009%

    No Known Activations