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

    Neuronpedia

    INDEX
    Explanations

    specific contexts and related outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2183>
    0.35
    ⋆
    0.35
     రచ
    0.35
    mdb
    0.34
     ODBC
    0.33
     теркәлүсез
    0.32
    ীভূত
    0.32
    <unused2126>
    0.32
    three
    0.31
    筤
    0.31
    POSITIVE LOGITS
    ologically
    0.36
     impuls
    0.35
     implications
    0.35
    などで
    0.35
     kontek
    0.35
     influencia
    0.34
     (
    0.34
     impulso
    0.33
     dictates
    0.33
    所の
    0.32
    Act Density 0.257%

    No Known Activations