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

    Neuronpedia

    INDEX
    Explanations

    alternative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .OK
    -0.07
     uncompressed
    -0.07
     повинен
    -0.07
    .FirebaseAuth
    -0.06
     compression
    -0.06
     spam
    -0.06
     Ferguson
    -0.06
     hung
    -0.06
     cohesion
    -0.06
     seal
    -0.06
    POSITIVE LOGITS
     alternative
    0.18
     Alternative
    0.14
    Alternative
    0.14
    alternative
    0.14
     alternatives
    0.13
    Alternatively
    0.08
     alternatively
    0.08
    ervative
    0.08
     alternate
    0.08
     Altern
    0.08
    Act Density 0.014%

    No Known Activations