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

    Neuronpedia

    INDEX
    Explanations

    mandatory requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cél
    0.44
    ெய்
    0.42
     shortcut
    0.42
    ുകയായിരുന്നു
    0.40
     casual
    0.40
    ின்றது
    0.40
     masterful
    0.39
     ചെറു
    0.39
     žel
    0.38
     polyhedron
    0.38
    POSITIVE LOGITS
     mandatory
    1.68
    mandatory
    1.48
     required
    1.41
     mandated
    1.39
     obligatorio
    1.37
     обяза
    1.34
     requirement
    1.32
     obligatoire
    1.32
     Mandatory
    1.31
    required
    1.30
    Act Density 0.047%

    No Known Activations