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

    Neuronpedia

    INDEX
    Explanations

    LM Studio for beginners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بالع
    0.38
    careers
    0.36
    ulé
    0.35
    ţă
    0.35
    career
    0.35
    )(&
    0.34
    Pale
    0.34
     Pale
    0.34
     bandera
    0.34
     Kxd
    0.34
    POSITIVE LOGITS
     Robot
    0.55
     LM
    0.55
    LM
    0.51
    Robot
    0.50
    Lm
    0.45
    Fore
    0.45
     Fore
    0.43
     LCM
    0.43
    Lc
    0.43
     Robo
    0.42
    Act Density 0.025%

    No Known Activations