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

    Neuronpedia

    INDEX
    Explanations

    Terraform provider versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ൂര്‍
    0.41
    цыяна
    0.40
    ᓛ
    0.37
     yoj
    0.37
     Carlson
    0.36
     WATTS
    0.36
    暮
    0.36
    htaking
    0.36
    ൂർ
    0.35
    璺
    0.35
    POSITIVE LOGITS
     outras
    0.39
    postgres
    0.38
    enci
    0.36
     Blackboard
    0.35
    ---
    0.35
    ),
    0.34
     পছন্দের
    0.34
     other
    0.33
    "),
    0.33
     ---
    0.33
    Act Density 0.001%

    No Known Activations